Trained for 12 epochs and 7400 steps.

Trained with datasets ['text-embed-cache', 'marsden-hartley-Flux-CC-512', 'marsden-hartley-Flux-CC-1024', 'marsden-hartley-Flux-CC-512-crop', 'marsden-hartley-Flux-CC-1024-crop']
Learning rate 0.0004, batch size 2, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: black-forest-labs/FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bfa51270d7d4d8f5fa27fe076f33d3d2121f9c02dcf5e4aa4b6d718666886a
+oid sha256:16b323ec90240b7477152f5bfa6499f6a200a4b7e4dc80ab0bfe14db80ea19c2
 size 109535132